Fishaudio: S2 Pro

fishaudio/s2-pro

Context

Input

text

Output

audio

Tool calling

Not listed

About this model

Fish Audio S2 Pro is an advanced 4B parameter open-weight text-to-speech model built on a dual-autoregressive architecture. It supports approximately 80 languages and introduces fine-grained, word-level inline tag control, allowing users to embed open-ended natural language instructions inside square brackets directly in the script (e.g., [whispering], [pitch up]). It outputs 44.1 kHz audio and natively supports zero-shot voice cloning from a reference clip.

Compare Speech-to-Text Models Compare Text-to-Speech Models Compare Audio Models

Input modalities

text

Accepted as model input

Providers

Available routing options for this model through OneInfer.

openrouter

Available

Text to speech

$15.000 / 1M characters

Routing

OneInfer optimized

Pricing

Current OneInfer pricing for this model.

Usage	Price
Text to speechTTS	$15.000 / 1M characters

Performance

Published evaluation results associated with this model.

No benchmark data is listed for this model.

API example

Refer Documentation

curl -X POST https://api.oneinfer.ai/v1/ula/generate-audio \
  -H "Authorization: Bearer YOUR_JWT_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
  "provider": "openrouter",
  "model": "fishaudio/s2-pro",
  "prompt": "OneInfer makes AI inference simple.",
  "stream": false,
  "voice_id": "English_expressive_narrator",
  "format": "mp3"
}'